Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 6697
    Prev
    Next
    INDEX
    Explanations

    mentions of a particular female character

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the pronoun 'her'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ype
    -0.93
    ypes
    -0.90
    kefeller
    -0.90
    ornia
    -0.89
    arios
    -0.88
    VERTIS
    -0.76
    brush
    -0.70
    eers
    -0.70
    ollo
    -0.70
    ablishment
    -0.69
    POSITIVE LOGITS
    ding
    1.26
     own
    1.26
     daughter
    1.13
    metic
    1.12
     husband
    1.12
    cule
    1.09
     granddaughter
    1.06
    nia
    1.04
    ded
    1.02
     Majesty
    1.02
    Activations Density 0.113%

    No Known Activations